def test_name_tidy(self):
# remove improper comma
sort_name = display_name_to_sort_name("Bitshifter, Bob,")
assert "Bitshifter, Bob" == sort_name
# remove improper period
sort_name = display_name_to_sort_name("Bitshifter, Bober.")
assert "Bitshifter, Bober" == sort_name
# retain proper period
sort_name = display_name_to_sort_name("Bitshifter, B.")
assert "Bitshifter, B." == sort_name
def default_name(self, display_name):
shortened_name = self.primary_author_name(display_name)
return display_name_to_sort_name(shortened_name)
def cluster_has_record_for_named_author(
self, cluster, working_sort_name, working_display_name, contributor_data=None):
""" Looks through the xml cluster for all fields that could indicate the
author's name.
Don't short-circuit the xml parsing process -- if found an author name
match, keep parsing and see what else can find.
:return: a dictionary containing description of xml field
that matched author name searched for.
"""
match_confidences = {}
if not contributor_data:
contributor_data = ContributorData()
# If we have a sort name to look for, and it's in this cluster's
# sort names, great.
if working_sort_name:
for potential_match in self.sort_names_for_cluster(cluster):
match_confidence = contributor_name_match_ratio(potential_match, working_sort_name)
match_confidences["sort_name"] = match_confidence
# fuzzy match filter may not always give a 100% match, so cap arbitrarily at 90% as a "sure match"
if match_confidence > 90:
contributor_data.sort_name=potential_match
return match_confidences
# If we have a display name to look for, and this cluster's
# Wikipedia name converts to the display name, great.
if working_display_name:
wikipedia_name = self.extract_wikipedia_name(cluster)
if wikipedia_name:
contributor_data.wikipedia_name=wikipedia_name
display_name = self.wikipedia_name_to_display_name(wikipedia_name)
match_confidence = contributor_name_match_ratio(display_name, working_display_name)
match_confidences["display_name"] = match_confidence
if match_confidence > 90:
contributor_data.display_name=display_name
return match_confidences
# If there are UNIMARC records, and every part of the UNIMARC
# record matches the sort name or the display name, great.
unimarcs = self._xpath(cluster, './/*[local-name()="datafield"][@dtype="UNIMARC"]')
candidates = []
for unimarc in unimarcs:
(possible_given, possible_family,
possible_extra, possible_sort_name) = self.extract_name_from_unimarc(unimarc)
if working_sort_name:
match_confidence = contributor_name_match_ratio(possible_sort_name, working_sort_name)
match_confidences["unimarc"] = match_confidence
if match_confidence > 90:
contributor_data.family_name=possible_sort_name
return match_confidences
for name in (working_sort_name, working_display_name):
if not name:
continue
if (possible_given and possible_given in name
and possible_family and possible_family in name and (
not possible_extra or possible_extra in name)):
match_confidences["unimarc"] = 90
contributor_data.family_name=possible_family
return match_confidences
# Last-ditch effort. Guess at the sort name and see if *that's* one
# of the cluster sort names.
if working_display_name and not working_sort_name:
test_sort_name = display_name_to_sort_name(working_display_name)
for potential_match in self.sort_names_for_cluster(cluster):
match_confidence = contributor_name_match_ratio(potential_match, test_sort_name)
match_confidences["guessed_sort_name"] = match_confidence
if match_confidence > 90:
contributor_data.sort_name=potential_match
return match_confidences
# OK, last last-ditch effort. See if the alternate name forms (pseudonyms) are it.
if working_sort_name:
for potential_match in self.alternate_name_forms_for_cluster(cluster):
match_confidence = contributor_name_match_ratio(potential_match, working_sort_name)
match_confidences["alternate_name"] = match_confidence
if match_confidence > 90:
contributor_data.family_name=potential_match
return match_confidences
return match_confidences
def cluster_has_record_for_named_author(self,
cluster,
working_sort_name,
working_display_name,
contributor_data=None):
""" Looks through the xml cluster for all fields that could indicate the
author's name.
Don't short-circuit the xml parsing process -- if found an author name
match, keep parsing and see what else can find.
:return: a dictionary containing description of xml field
that matched author name searched for.
"""
match_confidences = {}
if not contributor_data:
contributor_data = ContributorData()
# If we have a sort name to look for, and it's in this cluster's
# sort names, great.
if working_sort_name:
for potential_match in self.sort_names_for_cluster(cluster):
match_confidence = contributor_name_match_ratio(
potential_match, working_sort_name)
match_confidences["sort_name"] = match_confidence
# fuzzy match filter may not always give a 100% match, so cap arbitrarily at 90% as a "sure match"
if match_confidence > 90:
contributor_data.sort_name = potential_match
return match_confidences
# If we have a display name to look for, and this cluster's
# Wikipedia name converts to the display name, great.
if working_display_name:
wikipedia_name = self.extract_wikipedia_name(cluster)
if wikipedia_name:
contributor_data.wikipedia_name = wikipedia_name
display_name = self.wikipedia_name_to_display_name(
wikipedia_name)
match_confidence = contributor_name_match_ratio(
display_name, working_display_name)
match_confidences["display_name"] = match_confidence
if match_confidence > 90:
contributor_data.display_name = display_name
return match_confidences
# If there are UNIMARC records, and every part of the UNIMARC
# record matches the sort name or the display name, great.
unimarcs = self._xpath(
cluster, './/*[local-name()="datafield"][@dtype="UNIMARC"]')
candidates = []
for unimarc in unimarcs:
(possible_given, possible_family, possible_extra,
possible_sort_name) = self.extract_name_from_unimarc(unimarc)
if working_sort_name:
match_confidence = contributor_name_match_ratio(
possible_sort_name, working_sort_name)
match_confidences["unimarc"] = match_confidence
if match_confidence > 90:
contributor_data.family_name = possible_sort_name
return match_confidences
for name in (working_sort_name, working_display_name):
if not name:
continue
if (possible_given and possible_given in name
and possible_family and possible_family in name
and (not possible_extra or possible_extra in name)):
match_confidences["unimarc"] = 90
contributor_data.family_name = possible_family
return match_confidences
# Last-ditch effort. Guess at the sort name and see if *that's* one
# of the cluster sort names.
if working_display_name and not working_sort_name:
test_sort_name = display_name_to_sort_name(working_display_name)
for potential_match in self.sort_names_for_cluster(cluster):
match_confidence = contributor_name_match_ratio(
potential_match, test_sort_name)
match_confidences["guessed_sort_name"] = match_confidence
if match_confidence > 90:
contributor_data.sort_name = potential_match
return match_confidences
# OK, last last-ditch effort. See if the alternate name forms (pseudonyms) are it.
if working_sort_name:
for potential_match in self.alternate_name_forms_for_cluster(
cluster):
match_confidence = contributor_name_match_ratio(
potential_match, working_sort_name)
match_confidences["alternate_name"] = match_confidence
if match_confidence > 90:
contributor_data.family_name = potential_match
return match_confidences
return match_confidences